© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 108135
    Prev
    Next
    INDEX
    Explanations

    numerical data or financial ratios related to company performance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ÌĢ
    -0.07
    azor
    -0.07
    953
    -0.06
    ınca
    -0.06
    isure
    -0.06
     Th
    -0.06
    év
    -0.06
    rex
    -0.06
    unas
    -0.06
    _stderr
    -0.06
    POSITIVE LOGITS
    ahat
    0.07
    jedn
    0.07
    èĥ½å¤Ł
    0.07
     Horny
    0.06
    ashtra
    0.06
    aster
    0.06
    ought
    0.06
    ensch
    0.06
    ij
    0.06
    uke
    0.06
    Activations Density 0.000%

    No Known Activations